Skip to main content
AF3 Chain-Pair Protein-DNA ipTM
License: This constraint can use multiple tools, each under its own license. See the Tools Used tab and each tool’s page for license details.

This constraint is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

evo-design/proto-language/proto_language/constraint/protein_structure/af3_chain_pair_prot_dna_iptm_constraint.py
View source
Constraint contributors
Score protein-DNA ipTM from a per-chain-pair ipTM matrix. For each candidate complex:
  1. Separate protein and DNA sequences from the input tuple.
  2. Build a complex with num_protein_copies protein chains and all DNA chains (optionally adding the reverse complement).
  3. Run the configured structure predictor and read chain_pair_iptm.
  4. Pick out the protein-to-DNA entries and aggregate (max or mean).
  5. Score: 0.0 (best) when aggregated ipTM >= desired_iptm, 1.0 (worst) when ipTM is 0.
When the predictor does not expose the per-chain-pair ipTM matrix this raises RuntimeError: overall ipTM is not a valid substitute. Supported tools: any DNA-capable StructureBasedConstraintConfig predictor; AlphaFold3 and Protenix emit the per-chain-pair ipTM matrix under chain_pair_iptm, and Boltz-2 emits the same matrix under pair_chains_iptm.

​
API Reference

ConfigAF3ChainPairProtDNAIPTMConfig Source
Config for the AF3 chain-pair protein-DNA ipTM constraint.Runs a structure prediction for the protein-DNA complex and extracts the pairwise chain ipTM matrix. Only the protein-to-DNA entries are kept; the result is aggregated via aggregation (default: max over all protein-DNA chain pairs — both dimer halves, and both DNA strands when include_reverse_complement is set), then scored against desired_iptm.
The per-chain-pair ipTM matrix (chain_pair_iptm) is exposed by both AlphaFold3 and Protenix. Boltz-2 exposes the same matrix under pair_chains_iptm. A tool that does not surface the matrix raises a RuntimeError — overall ipTM is not a valid substitute.
​
integer
default:"2"
Protein monomer copies in the complex (2=homodimer, 1=monomer); reuses input chains first.
​
enum
default:"protein-dna"
Interface scored: ‘protein-dna’ (protein-DNA ipTM) or ‘protein-protein’ (homodimer ipTM).Options: protein-dna, protein-protein
​
number
default:"0.7"
Target protein-DNA chain-pair ipTM. Score is 0 when achieved.
​
enum
default:"max"
Aggregate protein-DNA chain-pair ipTM: ‘max’ (best pair) or ‘mean’ (average of pairs).Options: max, mean
​
boolean
default:"False"
Add the reverse-complement DNA strand when the input has only one DNA sequence.
​
enum
default:"alphafold3"
Predictor for the protein-DNA complex; must be DNA-capable (alphafold3/boltz2/protenix).Options: esmfold, esmfold2, alphafold3, boltz2, chai1, protenix, alphafold2, alphafold2_binder
​
ESMFoldConfig
Configuration for ESMFold structure prediction.
​
ESMFold2Config
Configuration for ESMFold2 structure prediction.
​
AlphaFold3Config
Configuration for AlphaFold3 structure prediction.
​
Boltz2Config
Configuration for Boltz2 structure prediction.
​
Chai1Config
Configuration for Chai1 structure prediction.
​
ProtenixConfig
Configuration for Protenix structure prediction.
​
AlphaFold2Config
Configuration for the general AlphaFold2 multimer structure predictor.
​
AlphaFold2BinderStructureConfig
Configuration for the AF2 binder-design backend.
ReturnsConstraintOutput
Per-proposal score in [0, 1] (lower is better) with prot_dna_iptm / prot_prot_iptm / overall_iptm metadata and the predicted Structure on slot 0.

​
Usage

Programming a protein-DNA operator complex with Protenix:
python

​
Metadata